© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 104398
    Prev
    Next
    INDEX
    Explanations

    recurring patterns related to time and identifiers in a business or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossa
    -0.07
    ÃŃl
    -0.07
    idor
    -0.06
    áo
    -0.06
    IGO
    -0.06
    ùa
    -0.06
    oS
    -0.06
    mani
    -0.06
    ado
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
    ↵
    0.09
    _exempt
    0.08
    orns
    0.07
     ÙħÛĮÙĦادÛĮ
    0.07
    haft
    0.07
    ibble
    0.07
    -Ta
    0.07
    -BEGIN
    0.07
    .ribbon
    0.07
    hões
    0.07
    Activations Density 0.051%

    No Known Activations